Expose relative cost of models in UI

Resolved 💬 7 comments Opened Apr 29, 2026 by alexandre-leng Closed Apr 29, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What variant of Codex are you using?

codex app

What feature would you like to see?

Hi everyone,

Here’s a simple idea: not every request needs the most powerful model.

Right now, using AI can feel like driving a supercar just to run everyday errands. It works, but it’s often more than necessary, and it comes at a higher cost. For many basic tasks like quick questions, small edits, or simple reasoning, a lighter and more efficient model would be enough. Yet we often default to the most advanced option, which uses more tokens and shortens subscription value.

What could really improve the experience is giving users control over the level of intelligence they use, depending on the task.

Imagine being able to choose:

A lightweight model for simple tasks, using fewer tokens 0.25x TOKEN
A balanced model for more structured work 0.5x TOKEN
A full-capability model for complex problems 1x token

0.25x Token 0.5x Token and 1x token would appear in the interface to encourage developers and users to choose the right model and think about the level of complexity and intelligence they actually need. There’s no point in using a Ferrari to go grocery shopping. For simple tasks like translation, a much lighter model is more than enough.

Same credits, but used more efficiently.

This would allow users to rely on powerful models only when necessary, and use lighter ones the rest of the time. The result is clear: longer-lasting subscriptions, better cost control, and reduced compute usage.

At scale, this also has an environmental benefit, as it avoids unnecessary energy consumption.

More importantly, it introduces a different mindset. Instead of always using the most advanced model, users can focus on using the most appropriate one. The right level of intelligence for the right task.

This approach makes AI more practical, more sustainable, and better aligned with real needs.

In the end, most of us don’t need maximum power all the time. We just need the right amount, at the right moment.

Adding this kind of control directly into the interface would make a real difference.

Have a nice day
Alexander

Additional information

_No response_

View original on GitHub ↗

7 Comments

github-actions[bot] contributor · 2 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #20078

Powered by Codex Action

alexandre-leng · 2 months ago

not a duplicate my ticket is an improve feature of https://github.com/openai/codex/issues/20078

etraut-openai contributor · 2 months ago

Codex already supports different models like you suggest. Refer to this documentation for details.

alexandre-leng · 2 months ago

@etraut-openai

Thanks for your reply.

I understand that Codex already supports multiple models. However, my suggestion is not about the existence of different models, but about their visibility and usability in the interface.

Currently, users don’t have a clear indication of the relative token consumption or cost factor when choosing a model. The system lacks a simple way to understand how expensive a model is compared to another in practical terms.

What I’m proposing is to make this explicit and intuitive, for example by displaying something like:

  • 0.25× token (lightweight)
  • 0.5× token (balanced)
  • 1× token (full capability)

This kind of indicator would:

  • Help users make informed decisions quickly
  • Encourage choosing the appropriate level of intelligence for the task
  • Improve cost efficiency and subscription longevity
  • Promote more responsible compute usage

So the key point is not model availability, but transparent consumption scaling directly in the UI, which is currently missing.

Thanks for considering this clarification.

etraut-openai contributor · 2 months ago

Thanks for the clarification. Reopening.

etraut-openai contributor · 2 months ago

I just noticed that you opened a new one. Thanks! Closing this as a duplicate.

alexandre-leng · 2 months ago

Thanks to you